Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions

<p dir="ltr">Rotating machines require bearings to operate smoothly. However, wear, misalignment, and poor lubrication can degrade bearings over time. Fault diagnosis models identify and classify bearing faults. A fault diagnosis model trained in a specific working condition may not...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Durjay Saha (21633095) (author)
مؤلفون آخرون: Md. Emdadul Hoque (20080485) (author), Muhammad E. H. Chowdhury (14150526) (author)
منشور في: 2024
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513545553575936
author Durjay Saha (21633095)
author2 Md. Emdadul Hoque (20080485)
Muhammad E. H. Chowdhury (14150526)
author2_role author
author
author_facet Durjay Saha (21633095)
Md. Emdadul Hoque (20080485)
Muhammad E. H. Chowdhury (14150526)
author_role author
dc.creator.none.fl_str_mv Durjay Saha (21633095)
Md. Emdadul Hoque (20080485)
Muhammad E. H. Chowdhury (14150526)
dc.date.none.fl_str_mv 2024-01-16T09:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2023.3347345
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Enhancing_Bearing_Fault_Diagnosis_Using_Transfer_Learning_and_Random_Forest_Classification_A_Comparative_Study_on_Variable_Working_Conditions/29445638
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Mechanical engineering
Information and computing sciences
Machine learning
Bearing fault
bearing fault classification
bearing fault classification under variable working conditions
machine condition monitoring
random forest
transfer learning
VGG16
Adaptation models
Fault diagnosis
Convolutional neural networks
Feature extraction
Employee welfare
Transfer learning
Condition monitoring
Random forests
dc.title.none.fl_str_mv Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Rotating machines require bearings to operate smoothly. However, wear, misalignment, and poor lubrication can degrade bearings over time. Fault diagnosis models identify and classify bearing faults. A fault diagnosis model trained in a specific working condition may not perform well in different working conditions. Real-world datasets are mixed with various work environment conditions; therefore, validating a model using different working conditions datasets is necessary. In this study, raw vibrational accelerometer data of variable working conditions is preprocessed using the window length and stride method to generate a data format suitable for evaluating the proposed model. This model employs the Transfer learning-based VGG16 model as the feature extractor and random forest as the classifier, and it has proven to be highly effective. This proposed fault diagnosis model adapts to different work environments and enhances fault classification at variable working conditions. The performance of the proposed model is evaluated using various metrics such as confusion matrix heatmap, t-SNE plot, precision-recall curve and learning curve. Results obtained from these metrics indicate that this model performs well compared to others. The overall accuracy of the model is 99.90%, and both the training and testing of this model are fast. It is evident from the learning curve evaluation that this model is free from over- or under-fitting issues. Overall, this model is reliable and suitable for classifying bearing faults at different working conditions and can be useable for real world purposes.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3347345" target="_blank">https://dx.doi.org/10.1109/access.2023.3347345</a></p>
eu_rights_str_mv openAccess
id Manara2_fd2ab77b068bce2f2751946f4beba105
identifier_str_mv 10.1109/access.2023.3347345
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29445638
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working ConditionsDurjay Saha (21633095)Md. Emdadul Hoque (20080485)Muhammad E. H. Chowdhury (14150526)EngineeringMechanical engineeringInformation and computing sciencesMachine learningBearing faultbearing fault classificationbearing fault classification under variable working conditionsmachine condition monitoringrandom foresttransfer learningVGG16Adaptation modelsFault diagnosisConvolutional neural networksFeature extractionEmployee welfareTransfer learningCondition monitoringRandom forests<p dir="ltr">Rotating machines require bearings to operate smoothly. However, wear, misalignment, and poor lubrication can degrade bearings over time. Fault diagnosis models identify and classify bearing faults. A fault diagnosis model trained in a specific working condition may not perform well in different working conditions. Real-world datasets are mixed with various work environment conditions; therefore, validating a model using different working conditions datasets is necessary. In this study, raw vibrational accelerometer data of variable working conditions is preprocessed using the window length and stride method to generate a data format suitable for evaluating the proposed model. This model employs the Transfer learning-based VGG16 model as the feature extractor and random forest as the classifier, and it has proven to be highly effective. This proposed fault diagnosis model adapts to different work environments and enhances fault classification at variable working conditions. The performance of the proposed model is evaluated using various metrics such as confusion matrix heatmap, t-SNE plot, precision-recall curve and learning curve. Results obtained from these metrics indicate that this model performs well compared to others. The overall accuracy of the model is 99.90%, and both the training and testing of this model are fast. It is evident from the learning curve evaluation that this model is free from over- or under-fitting issues. Overall, this model is reliable and suitable for classifying bearing faults at different working conditions and can be useable for real world purposes.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2023.3347345" target="_blank">https://dx.doi.org/10.1109/access.2023.3347345</a></p>2024-01-16T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2023.3347345https://figshare.com/articles/journal_contribution/Enhancing_Bearing_Fault_Diagnosis_Using_Transfer_Learning_and_Random_Forest_Classification_A_Comparative_Study_on_Variable_Working_Conditions/29445638CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/294456382024-01-16T09:00:00Z
spellingShingle Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
Durjay Saha (21633095)
Engineering
Mechanical engineering
Information and computing sciences
Machine learning
Bearing fault
bearing fault classification
bearing fault classification under variable working conditions
machine condition monitoring
random forest
transfer learning
VGG16
Adaptation models
Fault diagnosis
Convolutional neural networks
Feature extraction
Employee welfare
Transfer learning
Condition monitoring
Random forests
status_str publishedVersion
title Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
title_full Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
title_fullStr Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
title_full_unstemmed Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
title_short Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
title_sort Enhancing Bearing Fault Diagnosis Using Transfer Learning and Random Forest Classification: A Comparative Study on Variable Working Conditions
topic Engineering
Mechanical engineering
Information and computing sciences
Machine learning
Bearing fault
bearing fault classification
bearing fault classification under variable working conditions
machine condition monitoring
random forest
transfer learning
VGG16
Adaptation models
Fault diagnosis
Convolutional neural networks
Feature extraction
Employee welfare
Transfer learning
Condition monitoring
Random forests